© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14812
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical and health conditions, particularly those involving prevalence, procedures, or specific populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.58
    lète
    -0.56
     AppModule
    -0.53
    utives
    -0.53
     Waſſer
    -0.52
     المعيارى
    -0.52
    rawDesc
    -0.52
     Geiſt
    -0.51
    EndInit
    -0.51
    ôtel
    -0.50
    POSITIVE LOGITS
     abundancia
    0.52
     preponderance
    0.47
     abundance
    0.43
     prevalence
    0.43
     concentration
    0.39
     proliferation
    0.39
     abundante
    0.36
     emphasis
    0.36
     particularmente
    0.36
     abund
    0.35
    Activations Density 0.969%

    No Known Activations